Fast and Blind Speech Copy-Move Detection and Localization in Noise

TL;DR

This paper introduces a fast, blind speech copy-move detection method that effectively identifies tampered segments in noisy speech recordings without pre-segmentation, demonstrating high efficiency and robustness.

Contribution

The paper presents a novel local feature tensors-based algorithm transforming copy-move detection into tensor matching, with theoretical analysis and improved robustness against post-processing.

Findings

Efficient detection of short tampered segments in noisy speech.

Robustness against post-processing techniques.

Blind detection without pre-segmentation.

Abstract

Copy-move forgery on speech (CMF), coupled with post-processing techniques, presents a great challenge to the forensic detection and localization of tampered areas. Most of the existing CMF detection approaches necessitate pre-segmentation of speech to facilitate similarity calculations among these segments. However, these approaches usually suffer from the problems of uncontrollable computational complexity and sensitivity to the presence of a word that is read multiple times within a speech recording. To address these issues, we propose a local feature tensors-based CMF detection algorithm that can transform duplicate detection and localization problems into a special tensor-matching procedure, accompanied by complete theoretical analysis as support. Through extensive experimentation, we have demonstrated that our method exhibits computational efficiency and robustness against post-processing techniques. Notably, it can effectively and blindly detect tampered segments, even those as short as a fractional second. These advantages highlight the promising potential of our approach for practical applications.